© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 97801
    Prev
    Next
    INDEX
    Explanations

    entry point for code execution

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron responds to long runs of whitespace characters (indentation).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Actually
    -0.97
     obtuvo
    -0.90
    RectangleBorder
    -0.89
    นี้
    -0.89
    這個
    -0.88
    forChild
    -0.88
    CASH
    -0.88
    これは
    -0.87
    pfung
    -0.87
    beyaz
    -0.84
    POSITIVE LOGITS
    srand
    1.38
     welcome
    1.01
     while
    0.98
     乱
    0.94
     set
    0.93
    ate
    0.92
    ↵↵
    0.90
     startTime
    0.90
    set
    0.86
     seed
    0.86
    Activations Density 0.021%

    No Known Activations